Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1217
    Prev
    Next
    INDEX
    Explanations

    phrases related to political issues and advocacy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    87
    +0.46
    2.6%
    373
    +0.16
    0.9%
    481
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.46
    -0.01
    680
    +0.16
    0.04
    147
    +0.11
    0.05
    Negative Logits
    ".
    -0.73
    '.
    -0.69
    .<
    -0.67
    ''.
    -0.66
    .''.
    -0.65
    .(
    -0.65
    .''
    -0.64
    ".[
    -0.64
    .�
    -0.64
    .*
    -0.61
    POSITIVE LOGITS
     hindsight
    0.60
     Recession
    0.46
    ©¶æ
    0.45
    otom
    0.44
     conventions
    0.43
     rehearsal
    0.41
     deadline
    0.40
     lecture
    0.40
     stint
    0.40
     analogy
    0.40
    Activations Density 1.484%

    No Known Activations